IBM Research at the CoNLL 2018 Shared Task on Multilingual Parsing

Hui Wan, Tahira Naseem, Young-Suk Lee, Vittorio Castelli, Miguel Ballesteros


Abstract
This paper presents the IBM Research AI submission to the CoNLL 2018 Shared Task on Parsing Universal Dependencies. Our system implements a new joint transition-based parser, based on the Stack-LSTM framework and the Arc-Standard algorithm, that handles tokenization, part-of-speech tagging, morphological tagging and dependency parsing in one single model. By leveraging a combination of character-based modeling of words and recursive composition of partially built linguistic structures we qualified 13th overall and 7th in low resource. We also present a new sentence segmentation neural architecture based on Stack-LSTMs that was the 4th best overall.
Anthology ID:
K18-2009
Volume:
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Daniel Zeman, Jan Hajič
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
92–102
Language:
URL:
https://aclanthology.org/K18-2009
DOI:
10.18653/v1/K18-2009
Bibkey:
Cite (ACL):
Hui Wan, Tahira Naseem, Young-Suk Lee, Vittorio Castelli, and Miguel Ballesteros. 2018. IBM Research at the CoNLL 2018 Shared Task on Multilingual Parsing. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 92–102, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
IBM Research at the CoNLL 2018 Shared Task on Multilingual Parsing (Wan et al., CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-2009.pdf
Data
Universal Dependencies